Dual Adversarial Perturbators Generate rich Views for Recommendation

TL;DR

This paper introduces AvoGCL, a dual-adversarial graph learning method that employs curriculum learning to generate progressively challenging contrastive views, significantly improving recommendation performance.

Contribution

It proposes a novel dual-adversarial approach with curriculum learning to enhance contrastive view generation in graph-based recommender systems.

Findings

AvoGCL outperforms state-of-the-art methods on three real-world datasets.

The dual-adversarial and curriculum learning strategies improve contrastive view quality.

The method effectively balances view difficulty to prevent training collapse.

Abstract

Graph contrastive learning (GCL) has been extensively studied and leveraged as a potent tool in recommender systems. Most existing GCL-based recommenders generate contrastive views by altering the graph structure or introducing perturbations to embedding. While these methods effectively enhance learning from sparse data, they risk performance degradation or even training collapse when the differences between contrastive views become too pronounced. To mitigate this issue, we employ curriculum learning to incrementally increase the disparity between contrastive views, enabling the model to gain from more challenging scenarios. In this paper, we propose a dual-adversarial graph learning approach, AvoGCL, which emulates curriculum learning by progressively applying adversarial training to graph structures and embedding perturbations. Specifically, AvoGCL construct contrastive views by reducing graph redundancy and generating adversarial perturbations in the embedding space, and achieve better results by gradually increasing the difficulty of contrastive views. Extensive experiments on three real-world datasets demonstrate that AvoGCL significantly outperforms the state-of-the-art competitors.